Leveraging machine learning to deepen customer insight
Abstract
Banks have been sitting on troves of customer behavioural data for decades; only recently, however, have they had the computing power to find meaningful patterns in all these data. This article discusses how Scotiabank’s analytics team is using machine learning to better understand its customer base and identify meaningful events in its customers’ lives, like first job/employment, income change, starting or graduating college/ university, and family growth, thus improving the bank’s ability to provide contextual, personalised service and support. Understanding when customers are going through these life events makes it possible to deliver more meaningful contextual communication, and improve customer-centric service and support. This approach improves the customer experience and brand loyalty, translating into better marketing results and increased revenue for the bank.
The full article is available to subscribers to the journal.
Author's Biography
Zain Abbas He has a PhD in soft computing and uses data to help the bank meet its strategic ‘customer-first’ objective. Zain leverages machine learning and other advanced analytics to enhance Scotiabank’s knowledge about its customers and deliver a better customer experience.
Roland Merbis His team leverages advanced analytics techniques to better understand customer behaviour and intent. His team’s mandate supports Scotiabank Analytics’ mission to transform the bank into a data-centric organisation through impactful customer insights, innovative analytics and well-governed data.
Artur Motruk He is responsible for translating data in to action and insights, enabling the business to achieve tangible results from complex analyses. His degree in mathematics, combined with business acumen, assists the team in achieving return on investment from a variety of data initiatives.
Citation
Abbas, Zain, Merbis, Roland and Motruk, Artur (2020, May 1). Leveraging machine learning to deepen customer insight. In the Applied Marketing Analytics: The Peer-Reviewed Journal, Volume 5, Issue 4. https://doi.org/10.69554/TFEZ6835.
Publications LLP